Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AnthonyAlcaraz/agentic-graph-rag-skills --skill schema-pattern-selectorgit clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/schema-pattern-selector)<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/schema-pattern-selector"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/schema-pattern-selector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/schema-pattern-selector"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/schema-pattern-selector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00213 | $0.02245 |
| Opus 5 | $0.00106 | $0.01123 |
| Sonnet 5 | $0.00043 | $0.00449 |
| Haiku 4.5 | $0.00021 | $0.00225 |
Grade A, and why
schema-pattern-selector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schema Pattern Selector
Overview
Effective agent reasoning begins with schema patterns designed for machine cognition across temporal, contextual, and perspectival dimensions. Ch3 names four:
- Event-Centric — structure knowledge around occurrences, not static
entities. A
Meetingevent with participants, start/end timestamps, location, andhasPrecedingEvent/hasFollowingEventlinks. Enables "what meetings did Alice attend before the project review?" In DevOps: aDeploymentEventnode with timestamp + git commit + affected services (Example 3-14). - Contextual-Boundary — encapsulate information within explicit scopes. A
Context(Project-X)thatcontainstasks, isvalidDuringa time range, andappliesToa team. Prevents context mixing — the agent won't apply Task-1's facts to the wrong team or period. - Multi-Perspective — model contradictory viewpoints with attribution. A
Revenue-Forecastwhere Finance says 10M (confidence 0.8) and Sales says 12M (confidence 0.7), eachaccording-toa source. In DevOps: config drift where Terraform-state and AWS-api are two perspectives on the same setting. - Capability-Model — represent the agent's own capabilities, requirements, and authorization limits as queryable nodes. A support agent that can answer product questions (Public) but needs Supervisor authorization and a $500 limit to process refunds.
The selector matches a knowledge-shape description to the fitting pattern(s), flagging composition when several apply (Ch3 Tip: an event can carry multi-perspective viewpoints; a capability can be bounded by contextual constraints). The validator enforces each pattern's contract — the relationships and fields without which the pattern is broken: an event MUST have a temporal link (else it is just an entity); a context MUST declare a scope boundary; every perspective MUST attribute its value to a source with confidence in [0,1] (else contradiction-handling loses its attribution); every capability MUST declare an authorization level.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 151 lines · 213 tokens per session scan A 9809de2d24d1
schema-pattern-selector is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 213 tokens to every session and 2,245 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
lemmalog
Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints…
jurisd-research
Expert Australian/NZ legal research and AGLC4 citation using the jurisd MCP server. Use when finding cases or legislation (AustLII), looking up a provision offline, formatting or resolving citations, building a pinpoint, tracing who-cites-what, or producing an AGLC4 bibliography. Triggers on case law, legislation…
repo_search
Search repository text through a deterministic first-class fak command.
container-manager-kg-ingestion
Snapshot a host's Docker/Podman/Swarm inventory into the epistemic-graph knowledge graph as typed OWL nodes via the container-manager-mcp MCP server — containers, images, volumes, networks, swarm services and nodes, with their :usesImage / :runsOn / :builtFrom links. Use when the agent must record live container state…
cortex-design
Use this skill to generate well-branded interfaces and assets for Cortex, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.